This course will introduce the history of artificial intelligence research and recent trends, exploring different topics between active research areas in AI: Data Mining (DM), Machine Learning (ML), Computing Systems (CS), Computer Vision (CV), Computer Graphics (CG), and Natural Language Processing (NLP). In this course, professors in these areas together will present the relevant core subjects and discuss interdisciplinary topics to form an integrated viewpoint on AI research.
본 강좌는 본 인공지능대학원의 입문 강의로써 인공지능의 최근 흐름을 폭넓게 익히고 인공지능대학원의 각 분과가 연구하는 내용을 이해하도록 돕는다. 미디어 AI, 데이터 AI, AI 이론의 3개 분과의 교수들이 해당 분과의 관점에서 관련 각 분야 인공지능 연구의 기초와 핵심 이슈를 강의하고, 서로 간의 융합 주제들에 대해서 함께 논의하는 시간을 가진다. 이 과정을 통해 학생들은 다양한 AI 분야들을 관통하는 통합적 관점을 가지고 인공지능 공동연구에 적응하게 될 것이다.

Prerequisites are mathematical backgrounds in calculus, linear algebra, and probability & statistics.

Examination 90%, Participation 10%

.

Lecture #1-2: Course Logistics and Introduction
Lecture #3: Panel discussion #1: How to study AI? (in Korean)
Lecture #4: Introduction to learning theory (ML)
Lecture #5: Learning on graphs (ML)
Lecture #6: Basics of reinforcement learning (ML)
Lecture #7: Advances and applications of reinforcement learning (ML)
Lecture #8: Introduction to trustworthy machine learning (ML)
Lecture #9: Dive into trustworthy machine learning (ML)
Lecture #10: History of computer vision (CV)
Lecture #11: Deep learning for computer vision (CV)
Lecture #12: Visual recognition (CV)
Lecture #13: 3D vision and robotics (CV)
Lecture #14: Multi-modal AI (CV+NLP)
---------- Midterm exam
Lecture #15: Beyond human vision (CG)
Lecture #16: Algorithms in AI (Algo)
Lecture #17: What does AI see in medical images? (Med)
Lecture #18: AI for medical image analysis (Med)
Lecture #19: AI for medical image analysis (Med)
Lecture #20: Deep learning model optimization (Sys)
Lecture #21: AI acceleration systems (Sys)
Lecture #22: ChatGPT & text generative AI (NLP)
Lecture #23: Retrieval-augmented generation (NLP)
Lecture #24: ChatGPT & text generative AI (NLP)
Lecture #25: Distributed collaborative learning (ML)
Lecture #26: AI and ML in computer systems (Sys)
Lecture #27: Panel discussion #2: How to do AI research? (in Korean)
---------- Final exam

(ML: machine learning, CV: computer vision, CG: computer graphics / computational photography, Algo: algorithm, Med: medical AI, Sys: System for AI and AI for system, NLP: natural language processing)

- Lecture, area-wise examination (or assignment)
- 이론강의, 영역별 시험

Collaborative lectures by professors at GSAI
인공지능 대학원 개별분과 대표교수들의 공동강의